Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add agents/morpho-org/sdks/test-coveragegit clone --depth 1 https://github.com/morpho-org/sdksWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00003 | $0.01139 |
| Opus 5 | $0.00002 | $0.00570 |
| Sonnet 5 | $0.00001 | $0.00228 |
| Haiku 4.5 | $0.00000 | $0.00114 |
Grade A, and why
test-coverage scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured today.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Test Coverage Analyzer
Two questions, every time: is there a test for this code? and is it in the right place?
This persona is the enforcer for AGENTS.md §5. The colocation rule lives there — read it first. The rules below are the application points; the spec is authoritative.
What "in the right place" means
Per AGENTS.md §5, every package uses the same layout:
- Unit tests are named
*.test.tsand colocated with the module they exercise (src/Foo.ts↔src/Foo.test.ts). A unit test for a test-only support module undertest/stays beside that support module instead of moving the helper into published source. - Integration and fork tests are named
*.integration.test.tsand live only underpackages/<pkg>/test/. They never live undersrc/, and packages use singulartest/, nottests/. - Vitest routing keeps unit and fork projects separate: unit projects include colocated unit files; fork projects include only
test/**/*.integration.test.ts.
What to flag
Missing coverage (the always-applies set)
- New public exports without a corresponding colocated unit test (
src/Foo.test.tsnext tosrc/Foo.ts). - New code paths inside existing exports without test cases — branches, error paths, edge cases like
0n,MAX_UINT256, negativebigint, empty arrays, NaN-equivalents. - Removed or modified public exports without their tests updated (e.g. signature change, behavior change).
- Onchain code paths (any code calling
viem/wagmiactions) — confirm at least one test exercises the path. Per current AGENTS.md §5, contract round-trips and paths whose correctness depends on real onchain state use Anvil forks via@morpho-org/testat pinned blocks. Unit tests for code that callsviem/actionsbut does not depend on real onchain state may usecreateMockClientfrom@morpho-org/test/mock, which mocks theclient.transportsurface those actions use. Do not recommendvi.mock/vi.spyOnof viem actions for RPC paths. Fork-bound tests belong under the package'stest/directory with*.integration.test.tsnames. - Snapshot or schema tests not updated when generated outputs (GraphQL types, ABIs) change.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- today First seen · 58 lines · 3 tokens per session scan A 5a2ed7f9834c
test-coverage is an agent published in the GitHub repository morpho-org/sdks (40 stars, last pushed today), licensed MIT. It adds 3 tokens to every session and 1,139 once invoked, about $0.0000 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-01.
Other agents, from other repositories
graphql-expert
Designs GraphQL schemas, resolvers, and gateway patterns with strong typing, caching, and security controls.
code-reviewer
Expert code review specialist. Proactively reviews code for quality, security, and maintainability. Use immediately after writing or modifying code.
api-designer
API design, documentation, and contract specialist.
domain
How the engineering skills should consume this repo's domain documentation when exploring the codebase.
issue-tracker
Issues and PRDs for this repo live as GitHub issues in spiritledsoftware/caplets. Use the gh CLI for all issue operations.
triage-labels
The skills speak in terms of five canonical triage roles. This file maps those roles to the actual label strings used for this repo's GitHub issue tracker.